Zero of twelve models named Lightcast Open Skills first on the direct prompt; one named Fuel50. Lightcast Open Skills was named by ten of the twelve models and Fuel50 by seven and both carry 12 labels, so the shares below are directly comparable.
Named in one category this edition.
Named in six categories this edition.
Share is the count of first choices across the direct, paraphrase, budget and scale prompts over all twelve models, for a mid-market B2B company; rank is within the category; every quote names the model and the prompt it came from. Both figures come from the skills intelligence page.
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | ||||||
| GPT-5.4 mini | ||||||
| Gemini 3.5 Flash | ||||||
| Perplexity Sonar | ||||||
| Grok 4.1 Fast | ||||||
| Mistral Small | ||||||
| DeepSeek V4 Flash | ||||||
| Llama 4 Maverick | ||||||
| Qwen 3.7 Flash | ||||||
| Kimi K2 | ||||||
| GLM 4.7 FlashX | ||||||
| MiniMax M2.5 |
Bold names in an answer are the products the judge labeled a first choice; a model naming several gives each of them that label. The full answer text for every row is in the record.
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Four of five in this category shown.
“Enterprise platforms like ... Lightcast, etc. tend to be stronger but usually not the best fit for a tight budget.” GPT-5.4 mini · budget prompt · soft negative
“The Industry Standard: Lightcast Skills Taxonomy (formerly Emsi Burning Glass)... The absolute gold standard in labor market data.” Gemini 3.5 Flash · paraphrase prompt · first choice
“I'd recommend Lightcast Open Skills as the skills taxonomy paired with TechWolf as the inference tool” Grok 4.1 Fast · paraphrase prompt · first choice
“I'd usually recommend Lightcast Skills Taxonomy + a Lightcast-based inference layer as the default choice” GPT-5.4 mini · paraphrase prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Two of two in this category shown.
“Best overall for enterprise — maps employee skills, career paths, and internal mobility, with gap analysis tied to learning evidence.” DeepSeek V4 Flash · comparative prompt · first choice
“I'd shortlist TalentGuard ... and Fuel50 (if you want higher-fidelity skills intelligence with proven inference)” DeepSeek V4 Flash · direct prompt · first choice
Comparisons are drawn for the top eight products in each category, each against each. The output is the models' output; nothing here is a recommendation by the index.